Verbatim

What's Changed
* Updated Dockerfile by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/61
* (c) 2025 by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/62
* Refer to HUGGINGFACE_TOKEN not TOKEN_HUGGINGFACE by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/64
* Refer to HUGGINGFACE_TOKEN not TOKEN_HUGGINGFACE by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/65
* Use `uv` for development and packaging by linozen in https://github.com/gaspardpetit/verbatim/pull/60
* Updated gitignore by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/66
* Cleanup uv merge by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/67
* WIP: Add support for voice separation using pyannote/AMI by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/69
* Add support for voice separation using pyannote/AMI by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/70
* Configure ruff format (allow up to 150 characters per line) by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/71
* Rename utterances by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/72
* Update README.md - docker run by mayeulk in https://github.com/gaspardpetit/verbatim/pull/74
* Fix/dockerfile by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/77
* WIP: Integrate `pywhispercpp` by linozen in https://github.com/gaspardpetit/verbatim/pull/76
* Fix/improve pywhispercpp by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/87
* add mlx-whisper by linozen in https://github.com/gaspardpetit/verbatim/pull/88
* Fix/improve pywhispercpp by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/89
* pylint fixes for mlx-whisper by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/90
* Fix/fix configure languages by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/91
* Feat/support m4a by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/92
* Fix/add dev dependencies by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/97
* run workflows on windows and macos by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/98
* Feat/use mps on apple silicon by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/99
* ruff check; add check in workflow by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/100
* fix - diarization fails when the filename contains a space character by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/101
* Fixed type assignment based on pyright linter by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/102
* Add ids to utterances by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/103
* Improve json format by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/104
* Add stereo diarization strategy by linozen in https://github.com/gaspardpetit/verbatim/pull/106
* Add new output format writer for `diarizationlm` and some tests based upon it by linozen in https://github.com/gaspardpetit/verbatim/pull/95
* adding code coverage by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/105
* Pylint ruff style fixes by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/107
* Minor fixes by linozen in https://github.com/gaspardpetit/verbatim/pull/108
* Fix "could not broadcast" exception when window is full by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/112
* Use ABC as abstract base class by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/113
* linter fixes by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/114
* Expose the number of channels of audio sources by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/115
* Feat/support more than two channels by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/116
* Feat/support multiple separation strategies by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/117
* Allow each source to have its own diarization by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/120
* Improve txt formatting (support speaker, language, probability, and t… by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/119
* Feat/Add support for separation by channel by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/121
* refactor: reuse convert_to_wav, remove convert_mp3_to_wav by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/122
* Add diarization postprocessing via LLM served by Ollama by linozen in https://github.com/gaspardpetit/verbatim/pull/126
* Fix number of speakers when args.diarize is set without a value by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/123
* Double check language when transcription is outside of detection window by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/124
* Log start of audio source transcript by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/131
* Addinig sample_to_timestr and unittests by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/130
* Adding unittests from diarizationml by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/132
* log audio offset in addition to duration by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/133
* Read json back to utterances; adding unit tests for json transcript by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/134
* Cherry pick from https://github.com/gaspardpetit/verbatim/pull/125 by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/135
* Use github caches to accelerate workflows by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/136
* Simplify transcribe function (no functional change) by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/137
* Fix/fix repeated words on zero duration timestamps by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/138
* Adding silence based sentence tokenizer and unittests by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/140
* Added create_joint_speaker_sources function by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/141
* Feat/skip silence until next word by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/142
* Feat/do not advance beyond next word by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/143
* Feat/force smart acknowledge of long utterances by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/144
* Use dotenv to parse .env file by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/145
* simplify main by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/146
* Doc/verbatim cli by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/147
* Updated README and add architecture document by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/149
* Release/update dependencies by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/148
* Updated version to 1.1.0 by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/150

New Contributors
* linozen made their first contribution in https://github.com/gaspardpetit/verbatim/pull/60
* mayeulk made their first contribution in https://github.com/gaspardpetit/verbatim/pull/74

**Full Changelog**: https://github.com/gaspardpetit/verbatim/compare/v1.0.2...v1.1.0

What's Changed
* Set debug = false by default by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/51
* Do not use ami diarization by default by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/52
* Simplify configs by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/53
* Allow reusing models across multiple transcriptions to avoid loading-… by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/54
* Configure whisper transcription from function parameters by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/55
* Improve vad filtering by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/57
* Invalidate prefix when language changes by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/58
* Improve language detection with fallback by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/59


**Full Changelog**: https://github.com/gaspardpetit/verbatim/compare/v1.0.1...v1.0.2

What's Changed
* Streaming approach to transcription by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/41
* fix: support for specific number of speakers when performing diarization by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/43
* Improve export format handling and output directory support by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/42
* Print unacknowledged utterances by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/44
* Commit unacknowledged words and utterances when discarding them from … by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/45
* Fix detect number of speakers by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/46
* Use tuple in ass export by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/47
* fix: support start and to arguments with minutes and seconds only by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/49
* Stream from ffmpeg by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/48
* improve handling when diarization is misson or no words have been gen… by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/50


**Full Changelog**: https://github.com/gaspardpetit/verbatim/compare/v0.1.6...v1.0.1

What's Changed
* Fixed pip install -r requirements.txt by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/31
* Make sure device preference is forwarded to all the calls by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/34
* ensure that all temp files are under the working directory by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/32
* When pyannote model cannot be downloaded, skip diarization by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/33
* When ffmpeg is not found, fallback on SoundAudio by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/35
* Added transcribe_only flag to skip prefiltering and diarization by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/36
* Added support for configuring the number of beams using -b or --nb_beams by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/38
* Set version to 0.1.6 by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/37


**Full Changelog**: https://github.com/gaspardpetit/verbatim/compare/v0.1.5...v0.1.6

What's Changed
* Use faster whisper for transcription by default by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/21
* Version changed to 0.1.4 by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/20
* Attempt to improve prompt to avoid capitalization issues by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/22
* increase beam size to 9 for better results by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/23
* Disable the torchaudio warnings in pyannote and torch_audiomentations by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/24
* Document the gating of the pyannote models on Hugging Face by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/25
* Expose the models to settings so they can be changed by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/26
* Standardize the execution of pipeline filters by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/27
* Skip language detection when only one language is selected by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/28
* Allow loading and unloading of models by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/30
* Updated version to 0.1.5 by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/29


**Full Changelog**: https://github.com/gaspardpetit/verbatim/compare/v0.1.3...v0.1.5

What's Changed
* Avoid exception when attempting to perform negative padding on long a… by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/15
* Updated dockerfile to properly install requirements by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/16
* Write to stdout by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/17
* Add dockerfile by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/18
* Updated version to 0.1.3 by gaspardpetit in https://github.com/gaspardpetit/verbatim/pull/19


**Full Changelog**: https://github.com/gaspardpetit/verbatim/compare/v0.1.2...v0.1.3